react
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill's YAML frontmatter identifies 'Pedro Nauck' as the author, which differs from the provided context author 'marcioaltoe'. While this may be a result of forking or porting a community skill, the discrepancy is noted as it relates to identity metadata.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided React source code, which serves as an untrusted data source.
- Ingestion points: The agent uses the
Read,Grep, andGlobtools to access project files (e.g.,.tsx,.tsfiles). - Boundary markers: The instructions lack specific delimiters or warnings to ignore potential instructions embedded within the user's source code.
- Capability inventory: The agent can perform complex code transformations, provide architectural advice, and suggest state management patterns based on the ingested code.
- Sanitization: There is no explicit sanitization or validation of the ingested code content before it is processed by the agent's logic.
Audit Metadata